Neural Fuzzy System Research Articles

Outdoor Temperature Estimation Using ANFIS for Soft Sensors

<p>In recent years, several studies using smart methods and soft computing in the field of HVAC systems have been provided. In this paper, we propose a framework which will strengthen the benefits of the Fuzzy Logic (FL) and Neural Fuzzy (NF) systems to estimate outdoor temperature. In this regard, Adaptive Neuro Fuzzy Inference System (ANFIS) is used in effective combination of strategic information for estimating the outdoor temperature of the building. A novel versatile calculation focused around ANFIS is proposed to adjust logical progressions and to weaken the questionable aggravation of estimation information from multisensory. Due to ANFIS accuracy in specialized predictions, it is an effective device to manage vulnerabilities of each experiential framework. The NF system can concentrate on measurable properties of the samples throughout the preparation sessions. Reproduction results demonstrate that the calculation can successfully alter the framework to adjust context oriented progressions and has solid combination capacity in opposing questionable data. This sagacious estimator is actualized utilizing Matlab and the exhibitions are explored. The aim of this study is to improve the overall performance of HVAC systems in terms of energy efficiency and thermal comfort in the building.</p>

Outdoor Temperature Estimation Using ANFIS for Soft Sensors

<p>In recent years, several studies using smart methods and soft computing in the field of HVAC systems have been provided. In this paper, we propose a framework which will strengthen the benefits of the Fuzzy Logic (FL) and Neural Fuzzy (NF) systems to estimate outdoor temperature. In this regard, Adaptive Neuro Fuzzy Inference System (ANFIS) is used in effective combination of strategic information for estimating the outdoor temperature of the building. A novel versatile calculation focused around ANFIS is proposed to adjust logical progressions and to weaken the questionable aggravation of estimation information from multisensory. Due to ANFIS accuracy in specialized predictions, it is an effective device to manage vulnerabilities of each experiential framework. The NF system can concentrate on measurable properties of the samples throughout the preparation sessions. Reproduction results demonstrate that the calculation can successfully alter the framework to adjust context oriented progressions and has solid combination capacity in opposing questionable data. This sagacious estimator is actualized utilizing Matlab and the exhibitions are explored. The aim of this study is to improve the overall performance of HVAC systems in terms of energy efficiency and thermal comfort in the building.</p>

Adaptive neural fuzzy reasoning method for recognizing human movement gait phase

In response to the needs of real-time and accurate detection of the human gait phase for lower limb exoskeleton, the movement of the human foot is taken as the research object, and the human gait phase division method based on human kinematics and dynamics information is studied. This paper presents a wearable foot gait analysis system based on inertial sensors and pressure sensors, and studies the human gait phase recognition method based on plantar acceleration and plantar pressure information. Based on the analysis of the relationship between the plantar acceleration–pressure information and the gait period, the adaptive neural fuzzy reasoning system is used to integrate the information of plantar acceleration and plantar pressure information so as to realize the fast gait phase division. The three proposed methods are compared with the standard results of the Vicon motion capture system by experiments. The experimental results show that the accuracy of the ANFIS method combining the acceleration information and the plantar pressure information to the human gait phase division is 99.16%.

Prediction Model for Geologically Complicated Fault Structure Based on Artificial Neural Network and Fuzzy Logic

The development and distribution of geologically complicated fault structure have the characteristics of uncertainty, randomness, ambiguity, and variability. Therefore, the prediction of complicated fault structures is a typical nonlinear problem. Neither fuzzy logic method nor artificial neural network alone can solve this problem well because the fuzzy method is generally not easy to realize adaptive learning function, and the neural network method is not suitable for describing sedimentary microfacies or geophysical facies. Therefore, taking the marginal subsags in the Jiyang Depression, Eastern China, as a study case, this paper uses the method of combining artificial neural network and fuzzy logic to study geologically complicated fault structure prediction model. This paper expounds on the research status and significance of geologically complicated fault structure prediction model, elaborates the development background, current status, and future challenges of artificial neural networks and fuzzy logic, introduces the method and principle of fuzzy neural network structure and fuzzy logic analysis algorithm, conducts prediction model design and implementation based on fuzzy neural network, proposes the learning algorithm of fuzzy neural network, analyzes the programming realization of fuzzy neural network, constructs complicated fault structure prediction model based on the artificial neural network and fuzzy logic, performs the fuzzy logic system selection of complicated fault structure prediction model, carries out the artificial neural network structure design of complicated fault structure prediction model, compares the prediction effects of the geologically complicated fault structure model based on artificial neural networks and fuzzy logic, and finally discusses the system design and optimization of the prediction model for geologically complicated fault structures. The study results show that the fuzzy neural network fully integrates the advantages of artificial neural network and fuzzy logic system; based on the clear physical background of fuzzy logic system, it effectively integrates powerful knowledge expression ability and fuzzy reasoning ability into the network knowledge structure of neural network, which greatly improves the prediction accuracy of geologically complicated fault structure.

Towards Increasing Hosting Capacity of Modern Power Systems through Generation and Transmission Expansion Planning

The use of renewable and sustainable energy sources (RSESs) has become urgent to counter the growing electricity demand and reduce carbon dioxide emissions. However, the current studies are still lacking to introduce a planning model that measures to what extent the networks can host RSESs in the planning phase. In this paper, a stochastic power system planning model is proposed to increase the hosting capacity (HC) of networks and satisfy future load demands. In this regard, the model is formulated to consider a larger number and size of generation and transmission expansion projects installed than the investment costs, without violating operating and reliability constraints. A load forecasting technique, built on an adaptive neural fuzzy system, was employed and incorporated with the planning model to predict the annual load growth. The problem was revealed as a non-linear large-scale optimization problem, and a hybrid of two meta-heuristic algorithms, namely, the weighted mean of vectors optimization technique and sine cosine algorithm, was investigated to solve it. A benchmark system and a realistic network were used to verify the proposed strategy. The results demonstrated the effectiveness of the proposed model to enhance the HC. Besides this, the results proved the efficiency of the hybrid optimizer for solving the problem.

Monitoring and Prediction of the changes in water zone of wetlands using an intelligent neural-fuzzy system based on data from Google Eearth Engine system (Case study of Anzali Wetland, 2000-2019)

Monitoring and Prediction of the changes in water zone of wetlands using an intelligent neural-fuzzy system based on data from Google Eearth Engine system (Case study of Anzali Wetland, 2000-2019)

Research on Robot Fuzzy Neural Network Motion System Based on Artificial Intelligence.

An intelligent controller based on a self-learning interval type-II fuzzy neural network is proposed to make the motion controller of the industrial intelligent robot with good adaptability. This controller has a parallel structure and contains an interval type-II fuzzy neural network and a conventional PD controller. For the design of the interval type-II fuzzy neural network, the interval type-II fuzzy set is established using the slave design method. In the design process of the interval type-II fuzzy set of the front piece, a dual sequence symmetric trapezoidal subordinate function arrangement method is proposed, which makes the self-learning law and stability analysis of the system in an analytic form and facilitates the implementation of the algorithm in hardware. In the design of the neural network self-learning law, a parametric self-learning algorithm based on sliding mode control theory is established to adjust the structural parameters of the interval type-II fuzzy neural network online, and the stability of the system is proved by using Lyapunov's stability theorem. Three sets of validation simulation experiments are given in conjunction with the trajectory tracking problem of the Delta parallel robot. The simulation results show that, in the presence of system uncertainty, the intelligent controller based on interval self-learning interval type-II fuzzy neural network can significantly improve the trajectory tracking accuracy and robustness of the system and make the control system highly adaptable to the environment. Experiments of intelligent control system based on self-learning interval type-II fuzzy neural network and experiments of reusable particle swarm optimal motion planning method are designed, and the effectiveness of the intelligent control system and motion planning method is verified on the experimental platform. The experimental results show that the intelligent control system based on the self-learning interval type-II fuzzy neural network can effectively improve the accuracy and stability of robot trajectory tracking control, and the reusable particle swarm optimal motion planning method can quickly solve the robot motion planning problem with complex constraints online.

Fuzzy Neural Network Expert System with an Improved Gini Index Random Forest-Based Feature Importance Measure Algorithm for Early Diagnosis of Breast Cancer in Saudi Arabia

Breast cancer is one of the common malignancies among females in Saudi Arabia and has also been ranked as the one most prevalent and the number two killer disease in the country. However, the clinical diagnosis process of any disease such as breast cancer, coronary artery diseases, diabetes, COVID-19, among others, is often associated with uncertainty due to the complexity and fuzziness of the process. In this work, a fuzzy neural network expert system with an improved gini index random forest-based feature importance measure algorithm for early diagnosis of breast cancer in Saudi Arabia was proposed to address the uncertainty and ambiguity associated with the diagnosis of breast cancer and also the heavier burden on the overlay of the network nodes of the fuzzy neural network system that often happens due to insignificant features that are used to predict or diagnose the disease. An Improved Gini Index Random Forest-Based Feature Importance Measure Algorithm was used to select the five fittest features of the diagnostic wisconsin breast cancer database out of the 32 features of the dataset. The logistic regression, support vector machine, k-nearest neighbor, random forest, and gaussian naïve bayes learning algorithms were used to develop two sets of classification models. Hence, the classification models with full features (32) and models with the 5 fittest features. The two sets of classification models were evaluated, and the results of the evaluation were compared. The result of the comparison shows that the models with the selected fittest features outperformed their counterparts with full features in terms of accuracy, sensitivity, and sensitivity. Therefore, a fuzzy neural network based expert system was developed with the five selected fittest features and the system achieved 99.33% accuracy, 99.41% sensitivity, and 99.24% specificity. Moreover, based on the comparison of the system developed in this work against the previous works that used fuzzy neural network or other applied artificial intelligence techniques on the same dataset for diagnosis of breast cancer using the same dataset, the system stands to be the best in terms of accuracy, sensitivity, and specificity, respectively. The z test was also conducted, and the test result shows that there is significant accuracy achieved by the system for early diagnosis of breast cancer.

Fuzzy Logic-Based Systems for the Diagnosis of Chronic Kidney Disease.

Kidney failure occurs whenever the kidney stops to operate properly and would be unable to cleanse or refine the bloodstream as it should. Chronic kidney disease (CKD) is a potentially fatal consequence. If this condition is diagnosed early, its progression can be delayed. There are various factors that increase the likelihood of developing kidney failure. As a consequence, in order to detect this potentially fatal condition early on, these risk factors must be checked on a regular basis before the individual's health deteriorates. Furthermore, it lowers the cost of therapy. The chronic kidney or renal disease will be recognized in this work utilizing fuzzy and adaptive neural fuzzy inference systems. The fundamental purpose of this initiative is to enhance the precision of medical diagnostics used to diagnose illnesses. Nephron functioning, glucose levels, systolic and diastolic blood pressure, maturity level, weight and height, and smoking are all elements to consider while developing a fuzzy and adaptable neural fuzzy inference system. The output variable describes a specific patient's stage of chronic renal disease based on input factors such as stage 1, stage 2, stage 3, stage 4, and stage 5. The outcome will show the present stage of a patient's kidney. As a result, these methods can assist specialists in determining the stage of chronic renal disease. MATLAB software is used to create the fuzzy and neural fuzzy inference systems.

An efficient fruit quality monitoring and classification using convolutional neural network and fuzzy system

An efficient fruit quality monitoring and classification using convolutional neural network and fuzzy system

Predictive Modeling of Mechanical Properties of Silica Fume-Based Green Concrete Using Artificial Intelligence Approaches: MLPNN, ANFIS, and GEP.

Silica fume (SF) is a mineral additive that is widely used in the construction industry when producing sustainable concrete. The integration of SF in concrete as a partial replacement for cement has several evident benefits, including reduced CO2 emissions, cost-effective concrete, increased durability, and mechanical qualities. As environmental issues continue to grow, the development of predictive machine learning models is critical. Thus, this study aims to create modelling tools for estimating the compressive and cracking tensile strengths of silica fume concrete. Multilayer perceptron neural networks (MLPNN), adaptive neural fuzzy detection systems (ANFIS), and genetic programming are all used (GEP). From accessible literature data, a broad and accurate database of 283 compressive strengths and 149 split tensile strengths was created. The six most significant input parameters were cement, fine aggregate, coarse aggregate, water, superplasticizer, and silica fume. Different statistical measures were used to evaluate models, including mean absolute error, root mean square error, root mean squared log error and the coefficient of determination. Both machine learning models, MLPNN and ANFIS, produced acceptable results with high prediction accuracy. Statistical analysis revealed that the ANFIS model outperformed the MLPNN model in terms of compressive and tensile strength prediction. The GEP models outperformed all other models. The predicted values for compressive strength and splitting tensile strength for GEP models were consistent with experimental values, with an R2 value of 0.97 for compressive strength and 0.93 for splitting tensile strength. Furthermore, sensitivity tests revealed that cement and water are the determining parameters in the growth of compressive strength but have the least effect on splitting tensile strength. Cross-validation was used to avoid overfitting and to confirm the output of the generalized modelling technique. GEP develops an empirical expression for each outcome to forecast future databases’ features to promote the usage of green concrete.

Develop a Fuzzy System with LM/ODR Artificial Neural Network Model to Predict the Trend of Thermal Conductivity and Rheological Behavior for Graphene Aqueous-Based Nanofluid

Graphene is a flexible and transparent conductor which can be used in varied material-apparatus applications, counting solar cells, phones, touch panels, and light-emitting diodes (LED). In this study, to begin with, Graphene aqueous-based nanofluid is processed at separate mass fractions of 0.1 − 0.45 W%. Hence, thermal conductivity of these units was detected at separate temperatures of 25 − 50°C aside the KD2-Pro appliance. Similarly, Rheological behavior at noticed temperatures, for 12.23 and 122.3 S-1 shear rates, was detected aside the DV2EXTRA-Pro appliance. To shorten the expense of research, neural network designs and fuzzy system were trained to discover addition thermal conductivities and viscosities for unalike temperatures and mass fractions. Purpose of this study is to broaden Fuzzy system and ANN algorithms to predict the TC/VIS therefore it predicts the targeted-input dataset as factual as practicable. Hence, the numerical research was accomplished and related aside Levenberg Marquardt and Orthogonal Distance Regression models of Artificial Neural Networks, and Recursive Least Squares Fuzzy system. To train, 14400 data were placed. To test, 2160 ones, to train-control 2160 ones, and to train-output 10080 ones. Conclusions of comparison between algorithms and Fuzzy, exhibited Fuzzy system was fitted on the three-dimensional data more corrected than LM/ODR designs that leads to a better prediction.

Zoning of Drug Crimes and Evaluating and Modeling of Factors Affecting it Using Neural-Fuzzy System Technique (ANFIS)

Zoning of Drug Crimes and Evaluating and Modeling of Factors Affecting it Using Neural-Fuzzy System Technique (ANFIS)

Estimating algorithms for prediction and spread of a factor as a pandemic: a case study of global COVID-19 prevalence

Background: This paper presents open-source computer simulation programs developed for simulating, tracking, and estimating the COVID-19 outbreak. Methods: The programs consisted of two separate parts: one set of programs built in Simulink with a block diagram display, and another one coded in MATLAB as scripts. The mathematical model used in this package was the SIR, SEIR, and SEIRD models represented by a set of differential-algebraic equations. It can be easily modified to develop new models for the problem. A generalized method was adopted to simulate worldwide outbreaks in an efficient, fast, and simple way. Results: To get a good tracking of the virus spread, a sum of sigmoid functions was proposed to capture any dynamic changes in the data. The parameters used for the input (infection and recovery rate functions) are computed using the parameter estimation tool in MATLAB. Several statistic methods were applied for the rate function including linear, mean, root-mean-square, and standard deviation. In addition, an adaptive neuro-fuzzy inference system (ANFIS) is employed and proposed to train the model and predict its output. Conclusion: Due to the fact that COVID-19 disease has not been detected in a large part of the passengers, because they do not have any symptoms yet. For this purpose, in setting our forecast model, two scenarios are considered for the probability of a symptomatic person to travel until 1) the first medical visit 2) hospitalization. Therefore, in the present study, an open source toolbox for modeling, simulation and estimating the prevalence of coronavirus was presented. This procedure is presented in such a way that it can be generalized and applied in other parts and applications of estimating the scenarios of an event, including the potential of several models, including SIR, which is sensitive to pollution, etc. In addition, several statistical measures were used to determine the optimal time parameters for sigmoid functions. also, an adaptive fuzzy neural inference system was used to generate model output based on some of the training tasks applied to the system. This program can be used as an educational tool or for research studies and this article promises some lasting contributions to field of COVID-19.

Transferable representation modelling for real-time energy management of the plug-in hybrid vehicle based on k-fold fuzzy learning and Gaussian process regression

Electric vehicles, including plug-in hybrids, are important for achieving net-zero emission and will dominate road transportation in the future. Energy management, which optimizes the onboard energy usage, is a critical functionality of electric vehicles. It is usually developed following the model-based routine, which is conventionally costly and time-consuming and is hard to meet the increasing market competition in the digital era. To reduce the development workload for the energy management controller, this paper studies an innovative transfer learning routine. A new transferable representation control model is proposed by incorporating two promising artificial intelligence technologies, adaptive neural fuzzy inference system and Gaussian process regression, where the former applies k-fold cross valudation to build a neural fuzzy system for real-time implementation of offline optimization result, and the later connects the neural fuzzy system with a ‘deeper’ architecture to transfer the offline optimization knowledge learnt at source domain to new target domains. By introducing a concept of control utility that evaluates vehicle energy efficiency with a penalty on usage of battery energy, experimental evaluations based on the hardware-in-the-loop testing platform are conducted. Competitive real-time control ultility values (as much as 90% of offline benchmarking results) can be achieved by the proposed control method. They are over 27% higher than that achieved by the neural-network-based model.

Energy optimization of internet of things in wireless sensor network models using type‐2 fuzzy neural systems

SummaryIn this paper, type‐2 fuzzy logic design is employed to find the weight values of the radial basis function (RBF) neural network model, and thereby, the trained RBF neural network (RBFNN) model is intended to perform network energy optimization of the cloud‐assisted internet of things in wireless sensor networks (WSNs). RBF neural model comes under the class of feed forward neural network architecture and is a network with better generalization capability. RBFNN employs Gaussian activation function to determine the output of the network and the special feature of this activation function is that it follows a normal probability density function; hence it is a continuous activation function and provides better solutions than the other discrete activation functions. Due to which, in this work RBFNN is employed to determine network energy and to increase the life time of the network by selecting best cluster heads and also the network route. In RBFNN modelling, basically, the weights are initialized in a random manner, and this random initialization of weights at time results in the occurrences of global and local minima. The weights are tuned for their optimal values using type‐2 fuzzy model due to their capability of handling uncertainties, and since this problem of identifying optimal weight values of RBF neural model possesses highest level of uncertainties, type‐2 fuzzy system is applied here. Simulation process is done, and the results prove the effectiveness of the proposed approach in comparison with that of the existing approaches from previous literatures for the energy optimization problem.

Deep Neural Fuzzy System Oriented toward High-Dimensional Data and Interpretable Artificial Intelligence

Fuzzy systems (FSs) are popular and interpretable machine learning methods, represented by the adaptive neuro-fuzzy inference system (ANFIS). However, they have difficulty dealing with high-dimensional data due to the curse of dimensionality. To effectively handle high-dimensional data and ensure optimal performance, this paper presents a deep neural fuzzy system (DNFS) based on the subtractive clustering-based ANFIS (SC-ANFIS). Inspired by deep learning, the SC-ANFIS is proposed and adopted as a submodule to construct the DNFS in a bottom-up way. Through the ensemble learning and hierarchical learning of submodules, DNFS can not only achieve faster convergence, but also complete the computation in a reasonable time with high accuracy and interpretability. By adjusting the deep structure and the parameters of the DNFS, the performance can be improved further. This paper also performed a profound study of the structure and the combination of the submodule inputs for the DNFS. Experimental results on five regression datasets with various dimensionality demonstrated that the proposed DNFS can not only solve the curse of dimensionality, but also achieve higher accuracy, less complexity, and better interpretability than previous FSs. The superiority of the DNFS is also validated over other recent algorithms especially when the dimensionality of the data is higher. Furthermore, the DNFS built with five inputs for each submodule and two inputs shared between adjacent submodules had the best performance. The performance of the DNFS can be improved by distributing the features with high correlation with the output to each submodule. Given the results of the current study, it is expected that the DNFS will be used to solve general high-dimensional regression problems efficiently with high accuracy and better interpretability.

Prediction of emission and performance characteristics of reactivity-controlled compression ignition engine with the intelligent software based on adaptive neural-fuzzy and neural-network

A fuel reactivity-controlled compression ignition concept promises to overcome increasingly stringent emission standards with ultra-low nitrogen oxide and soot emissions and very high fuel efficiency. In the present work, it was developed an intelligent software-based on adaptive neural-fuzzy inference systems in order to predict the emission and performance values of reactivity-controlled compression ignition engine fueled with natural gas and diesel under different operating conditions through an experimentally validated computational fluid dynamics model with the four cases generated in the study for intelligent software-based on neural-fuzzy systems simulation considering different input and output parameters. The engine model was run at input variables as initial pressure (1.67–2.79 bar), total fuel mass (60–130 mg), exhaust gas recirculation ratio (0–20%), the start of injection (32–56° before top dead center) and total 180 different conditions were generated while output responses such as indicated power, maximum in-cylinder pressure, soot, and nitrogen oxide emissions. The main operating parameters of the reactivity-controlled compression ignition engine were determined for different load conditions, enabling the engine to operate in a wide range with high efficiency and low emission. For the neural-fuzzy inference model presented study, the different number Gaussian curve membership functions (5, 6, 7, 8) (gaussmf) have been used considering different adaptive neural-fuzzy cases, and generally, about 13500 training cycles is found to be optimum neural-fuzzy inference parameters and minimum error value. Mean square error, mean error percentage, and the absolute fraction of variance (R2) were used to assess and compare the performance of the adaptive neural-fuzzy and artificial neural network. Results of the adaptive neural-fuzzy confirm that the model successfully predicts the performance and emission of the engine with the R2 value % 99.8, %99.9, and %96.5 for the output parameters indicated power, maximum in-cylinder pressure, and nitrogen oxide, respectively. Moreover, the performance of the neural-fuzzy inference algorithm compared with artificial neural network and consequently, it was observed that neural-fuzzy inference gives more accurate predict value according to the artificial neural network. Moreover, generating a neural-fuzzy inference architecture using the proposed mathematical foundation given the study shows that neural-fuzzy inference is a very effective and helpful technique to predict the reactivity-controlled compression ignition engine performance and emission parameters.

Recognizing the take-off action pattern of basketball players based on fuzzy neural network system

Recognizing the take-off action pattern of basketball players based on fuzzy neural network system

Mechanical performance analysis of a piezoelectric ceramic friction damper and research of its semi-active control strategy

Based on piezoelectric ceramics' piezoelectric effect, a new type of piezoelectric ceramic friction damper (PCFD) is designed and manufactured to provide a reliable energy dissipation device for structural response control. In the PCFD, high-strength bolts limit the deformation of piezoelectric ceramics under voltage, and the resulting reaction force changes the preload of high-strength bolts, thereby realizing real-time adjustment of friction by adjusting the positive pressure on the friction surface. The influence of friction plates with different materials on the hysteretic performance of friction damper under different tightening torque is investigated by cyclic loading test to determine the friction plate's selection in the PCFD. The hysteretic performance test is carried out to evaluate the energy dissipation capacity of PCFD with different voltages, and the experimental results are compared with the theoretical values. The finite element model of PCFD is established to analyze the stress distribution of each component of the PCFD under different voltages. Based on the semi-active control characteristics of PCFD, the Takagi-Sugeno fuzzy neural network semi-active control system for frame structure with PCFD is designed. The adaptive learning function of the adaptive network-based fuzzy inference system (ANFIS) is used to generate fuzzy rules and fuzzy neural network controller (FNNC). Finally, the semi-active control simulation of three-storey frame structure model under seismic excitation is carried out by Simulink. The experimental and numerical results show that the PCFD designed in this paper has good energy dissipation capacity, and the maximum control force increases linearly with the increase of voltage. The combination of FNNC, which is established by ANFIS, and PCFD can effectively reduce the structure response.